Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    understanding language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ایسے
    0.48
    eseorang
    0.47
     UNIV
    0.47
     insect
    0.47
    ٹا
    0.46
    MPa
    0.46
    לט
    0.46
    precio
    0.45
     cupboard
    0.45
    removeItem
    0.44
    POSITIVE LOGITS
    2
    0.43
    that
    0.43
     décadas
    0.42
    八
    0.41
    on
    0.41
     Banking
    0.41
    新年
    0.40
    شرين
    0.40
    Particip
    0.40
    ats
    0.40
    Act Density 0.001%

    No Known Activations